McDaniel & Gates – Marketing Research, 9th Edition Instructor’s Manual
B. Basic Steps in Cluster Sampling
1. The population of interest is divided into mutually exclusive and exhaustive subsets.
a. One-stage cluster-if sample is from all elements in the subsets selected
b. Two-stage cluster sample–if a sample of elements is selected in some probabilistic manner
from the selected subsets
1) Units of geography–such as city blocks
2) Main assumption–elements in cluster are heterogeneous
b. Multistage area sampling or multistage area probability sampling–randomly select
geographic areas in progressively smaller units
4. Cluster Samples–are generally less statistically efficient than other types of probability
samples.
5. NONPROBABILITY SAMPLING METHODS
I. Nonprobability Sampling Methods Defined
A. Four Types of Nonprobability Sampling Techniques
1. Convenience Samples–used for reasons of convenience
a. Convenience sampling may be growing at a faster rate than the growth in the use of
2. Judgment Sample–applied to any situation in which the researcher is attempting to draw a
representative sample based on judgmental selection criteria.
3. Quota Samples–demographic characteristics of interest to the researcher are represented in
1) Respondents for a quota sample are not selected on a random basis, as they must be for a
2) In a stratified sample, the classification factors used for stratification must be selected on the
basis of the existence of a correlation between the classification factor and the behavior of
interest. Snowball Sampling–involves the selection of additional respondents on the basis of
referrals from the initial respondents.
a. Main advantage– the dramatic reduction in search costs
b. Disadvantage–reduction in sample quality
See Practicing Marketing Research: E-Mail Surveys of Web Site Usage—When
Snowballing Fails to Snowball (p 398)
Elaine Peterson, librarian and professor at Montana State University Libraries at Bozeman,
Montana, wanted to evaluate user response and opinion regarding the school’s popular digital
library called the Montana Natural Resource Information System (NRIS). She used the snowball
sampling approach in two stages: in-person interviews followed up a year later by e-mail surveys
Discussion Questions
2. What is the inherent difference between a telephone interview and e-mail survey as regards an
interviewee feeling comfortable giving names?
6. INTERNET SAMPLING
I. Internet Interviewing
A. Advantages of Internet Interviewing
1. Target Respondents–can complete the survey at their convenience
2. Data Collection–inexpensive
3. The Interview–administered under software control
4. The survey can be completed quickly
B. Disadvantages of Internet Interviewing
1. No scientific research regarding the representativeness of Internet samples–users of the
internet are not representative of the general population
3. Recruiting samples of consumers via Internet bulletin board postings or banner advertising on
4. Panels of individuals who have agreed to accept and complete email surveys are not
representative of the general population or of the users of the Internet
See Practicing Marketing Research: How Building a Blended Sample Can Help Improve
Research Results (p 400)
• SSI offers the following suggestions for creating a blended sample: Consider including
calibration questions— Look for existing external benchmarks for your survey topic.
• Understand the sample blending techniques used to create your sample—Tell your
Questions:
1. Beyond the variables discussed, can you think of any others that might be relevant when
creating a blended sample?
2. Do you think a blended sample would be useful, and if so would you be inclined to try it? Are
there any situations in which you would think a single-source sample would be more effective?
Why?
7. SUMMARY
QUESTIONS FOR REVIEW AND CRITICAL THINKING
1. What are some situations in which a census would be better than a sample? Why are
samples usually taken rather than censuses?
A census would be better than a sample when a business has only a small group of customers and
does not expect to acquire many more. Samples are usually less expensive to administer and are
2. Develop a sampling plan for examining undergraduate business students’ attitudes
toward Internet advertising.
• Determine the population: All undergraduate students that attend the university.
• Determine the sampling frame: A list of all undergraduate students divided by rank or
class level obtained from the registrar’s office
• Determine data collection method: Telephone survey
• Determine sampling method: A quota sample based on gender and class standing
3. Given an example of a perfect sample frame. Why is a telephone directory often not an
acceptable sample frame?
A perfect sample frame would be a mailing list or telephone list that perfectly represents the
population. For example, if you wished to interview all male individuals aged 25-45 who play
4. Distinguish between probability and nonprobability samples. What are the advantages
and disadvantages of each? Why are nonprobability samples so popular in marketing
research?
are: 1) expensive, 2) more complex design, and 3) it takes more time to execute.
Non probability samples do not ensure that each unit will have a known chance of being chosen.
3) results cannot be projected to the total population. Nonprobability samples are popular
5. Distinguish among a systematic sample, cluster sample, and stratified sample. Give
examples of each.
A systematic sampling procedure uses a skip interval which is calculated by dividing the total
population by the sample size. An example would be to collect data from 10 the name on a
6. What is the difference between a stratified sample and a quota sample?
There are two basic differences between a stratified and a quota sample. In a quota sample
respondents are not chosen randomly, in a stratified sample they are. In a stratified sample, the
7. American National Bank has 1,000 customers. The manager wishes to draw a sample of
100 customers. How would this be done using systematic sampling? What impact would it
have on the technique, if any, if the list were ordered by average size of deposit?
Using systematic sampling, a skip interval of 10 would be determined (1000/100). Every tenth
person would be chosen from the list to be included in the sample. If the distribution of the banks
8. Do you see any problem with drawing a systematic sample from a telephone book,
assuming that the telephone book is an acceptable sample from for the study in question?
9. Describe snowball sampling. Given an example of a situation in which you might use this
type of sample. Give an example of a situation in which you might use this type of sample.
What are the dangers associated with this type of sample?
10. Name some possible sampling frames for the following:
a. Patrons of sushi bars
A customer list from local restaurant owners or a list bought from a credit card company that
specifically contains charges at sushi restaurants.
b. Smokers of high-priced cigars
Customer list from a smoke shop of people who buy these items. There are mail order houses
c. Snowboarders
There are probably a couple magazines targeted at snowboarders, get their subscriber list. Mail-
d. Owners of DVD players
Customer list from computer companies who have sold DVD players. Obtain list of customers
who have rented DVD disks from Blockbuster or other rental company.
e. People that have visited one or more countries in Europe in the last year.
Travel agencies customer lists, passenger lists from airlines, or from the government agency
granting passports.
f. People who immigrated to the United States within the last two years.
g. People with allergies
A list of allergy specialists’ patients.
11. Identify the following sample designs:
McDaniel & Gates – Marketing Research, 9th Edition Instructor’s Manual
a. The names of 200 patrons of a casino are drawn from a list of visitors for the last month
and a questionnaire is administered to them.
Simple random sample
b. A radio talk show host invites listeners to call in and vote yes or no on whether handguns
should be banned.
Convenience sample
c. A dog food manufacturer wants to test a new dog food. It decides to select 100 dog
owners who feed their dog’s canned food, 100 who feed their dog’s dry food, and 100 who
feed their dog’s semi moist food.
Quota Sample
d. A poll surveys men who play golf to predict the outcome of a presidential election.
WORKING THE NET
1. Toluna offers QuickSurveys, a self-service tool that enables you to conduct market
research quickly, easily and cost effectively. You can:
• Create a survey of up to 5 questions.
• Select up-to 2,000 nationally representative respondents.
• Pay online using a credit card or PayPal.
• Immediately follow the results live online and complete within 24 hours (speed of
completion may vary by country.
With this system, once your survey has been created it will automatically appear live on
targeted specific areas of Toluna.com—a global community site that provides a forum
where over 4 million members interact and poll each other on a broad range of topics. Visit
www.toluna-group.com to view a QuickSurveys flash demo.
2. Throughout 2008, Knowledge Networks worked in conjunction with the Associated Press
and Yahoo to repeatedly poll 2,230 people (from random telephone sampling) about likely
election results and political preferences. Visit www.knowledgenetworks.com and evaluate
their methodology and ultimate accuracy (or inaccuracy) on this topic.
Answers should vary. However, as of November 2008, here are some details: An AP-Yahoo
News poll was conducted Nov. 4 and involved interviews with 1,352 adults. It had an overall
McDaniel & Gates – Marketing Research, 9th Edition Instructor’s Manual
telephone polling methods and followed with online interviews. People chosen for the study who
had no Internet access were given it for free.
Without knowing more demographics about those who responded online versus by phone, it is
REAL-LIFE RESEARCH
Case 13.1 The Research Group
Key Points:
• The Research Group has been hired by the National Internet Service Providers
Association to determine several things about customers’ choices of and interactions with
a particular Internet service provider (ISP).
Questions:
1. How would you describe this sampling methodology?
2. What problems do you see arising from this technique?
3. Suggest an alternative sampling method that might give the National Internet Service
Providers Association a better picture of the information it desired.
Case 13.2 New Mexico National Bank
Key Points:
1. New Mexico National Bank (NMNB) operates branches in 23 cities and towns throughout the
state of New Mexico.
3. New Mexico National Bank (NMNB) has 53,400 people in the state using its credit cards.
Questions:
1. How would you define the population of interest for the study?
2. What sampling frame(s) might you use for the project?
3. What procedure would you use to select a simple random sample from the sampling
frame you chose above?
4. Would it make sense to use a stratified sample in the situation? Why or why not? How
would you approach the process of developing a stratified sample from the sampling frame
you chose?
5. Could you use the sampling frame to draw a cluster sample? How would you go about
it? Would it make any sense to do this?
6. Which of the three probability sampling methods just mentioned would you choose for
this study? Why would you choose that option?